Evolving Goalkeeper Behaviours for Simulated Soccer Competition

Abstract

This paper describes our approach on evolving a robot controller to generate a set of goalkeeper behaviours in the Simulation League of the RoboCup competition. The goalkeeper agent is a software construct that performs in a simulated environment provided by the Soccer Server. The soccer server is a noisy environment provided as a testing ground for various artificial intelligence techniques used by different research teams around the world. Our experiments were set out to determine the conditions that need to be met for an evolved goalkeeper agent to perform adequately in a defensive situation. A framework was developed to test the agent's performance in the simulator. The results show that our approach was able to produce a robust robot controller.